Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    JavaScript and Python code snippets

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical or structured formats, likely related to statistical data or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /"
    -0.54
     stronger
    -0.53
     bicy
    -0.52
     synerg
    -0.52
     footwear
    -0.51
    bush
    -0.51
     cataly
    -0.51
     Forrest
    -0.49
     sorting
    -0.48
     gent
    -0.48
    POSITIVE LOGITS
    roma
    0.71
    thora
    0.69
     Detected
    0.66
    ESSION
    0.64
     Wraith
    0.64
    \":
    0.63
     ][
    0.60
    theless
    0.60
    Ĥª
    0.59
    ?????-?????-
    0.57
    Act Density 0.316%

    No Known Activations